Skip to content
Tech News
clear
Topics: Today This Week This Month This Year
31.
Gemma 4 12B: A unified, encoder-free multimodal model (news.ycombinator.com)
32.
A 10 year old Xeon is all you need (news.ycombinator.com)
33.
A 10 year old Xeon is all you need (for 26B-A4B MTP Drafters without GPU) (news.ycombinator.com)
34.
New Tools Strip AI Guardrails In Minutes, Allowing Them to Give Instructions on Chlorine Gas Attacks (futurism.com)
35.
Matrix Multiplications on GPUs Run Faster When Given "Predictable" Data (news.ycombinator.com)
36.
CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs (news.ycombinator.com)
37.
Indexing a year of video locally on a 2021 MacBook with Gemma4-31B (50GB swap) (news.ycombinator.com)
38.
KV Sharing, MHC, and Compressed Attention (news.ycombinator.com)
39.
Google’s underrated AI app unlocked 3 amazing on-device AI tools on my Android phone (androidauthority.com)
40.
Maker packs an opinionated, googly-eyed AI chatbot into a mobile suitcase, powered by an Nvidia Jetson — entirely local machine entity runs Gemma 4 E4B and can respond in 200ms (tomshardware.com)
41.
What's in a GGUF, besides the weights – and what's still missing? (news.ycombinator.com)
42.
Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model (news.ycombinator.com)
43.
Running local models on an M4 with 24GB memory (news.ycombinator.com)
44.
Diskless Linux boot using ZFS, iSCSI and PXE (news.ycombinator.com)
45.
Google's Gemma 4 AI models get 3x speed boost by predicting future tokens (arstechnica.com)
46.
Google’s latest trick gets Gemma 4 running 3x faster right on your phone (androidauthority.com)
47.
Accelerating Gemma 4: faster inference with multi-token prediction drafters (news.ycombinator.com)
48.
Show HN: TRiP – a complete transformer engine in C built from scratch just by me (news.ycombinator.com)
49.
Running local LLMs offline on a ten-hour flight (news.ycombinator.com)
50.
Running Local LLMs Offline on a Ten-Hour Flight (news.ycombinator.com)
51.
TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment (news.ycombinator.com)
52.
Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB) (news.ycombinator.com)
53.
CPUs Aren't Dead. Gemma2B Out Scored GPT-3.5 Turbo on Test That Made It Famous (news.ycombinator.com)
54.
Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference (news.ycombinator.com)
55.
Apple's accidental moat: How the "AI Loser" may end up winning (news.ycombinator.com)
56.
I ran Gemma 4 as a local model in Codex CLI (news.ycombinator.com)
57.
I tested Google’s upcoming Gemini Nano 4 — its faster, smarter AI isn’t what I expected (androidauthority.com)
58.
Has Mythos just broken the deal that kept the internet safe? (news.ycombinator.com)
59.
Google Gemma 4 in your pocket: How to run the latest AI fully offline (androidauthority.com)
60.
Show HN: Gemma 4 Multimodal Fine-Tuner for Apple Silicon (news.ycombinator.com)
Today's top topics: apple google openai airpods android authority tesla pixel 11 walmart netflix anthropic
View all today's topics →